publications

* denotes equal contribution.

2024

  1. Preprint
    Advancing LLM Reasoning Generalists with Preference Trees
    Lifan Yuan, Ganqu Cui, Hanbin Wang, Ning Ding, Xingyao Wang, Jia Deng, Boji Shan, Huimin Chen, Ruobing Xie, Yankai Lin, Zhenghao Liu, Bowen Zhou, Hao Peng, Zhiyuan Liu, and Maosong Sun
    Arxiv preprint, Apr 2024
    Paper Code X/Twitter Thread
  2. LLMAgents
    @ ICLR 2024     Oral
    Executable Code Actions Elicit Better LLM Agents
    Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, and Heng Ji
    LLMAgents Workshop @ ICLR 2024 (Oral), Feb 2024
    Paper Code Blog X/Twitter Thread Demo
  3. Preprint
    Text-Based Reasoning About Vector Graphics
    Zhenhailong Wang, Joy Hsu, Xingyao Wang, Kuan-Hao Huang, Manling Li, Jiajun Wu, and Heng Ji
    Arxiv preprint, Apr 2024
    Paper Website Code
  4. ICLR 2024
    MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
    Xingyao Wang*, Zihan Wang*, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng, and Heng Ji
    In Proceedings of the International Conference on Learning Representations, May 2024
    Paper Website Code Blog X/Twitter Thread
  5. ICLR 2024
    CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
    Lifan Yuan*, Yangyi Chen*, Xingyao Wang, Yi R. Fung, Hao Peng, and Heng Ji
    In Proceedings of the International Conference on Learning Representations, May 2024
    Paper Code
  6. LLMAgents
    @ ICLR 2024
    If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents
    Ke Yang, Jiateng Liu, John Wu, Chaoqi Yang, Yi Ren Fung, Sha Li, Zixuan Huang, Xu Cao, Xingyao Wang, Yiquan Wang, Heng Ji, and Chengxiang Zhai
    LLMAgents Workshop @ ICLR 2024, Jan 2024
    Paper
  7. Preprint
    Examining LLMs’ Uncertainty Expression Towards Questions Outside Parametric Knowledge
    Genglin Liu, Xingyao Wang, Lifan Yuan, Yangyi Chen, and Hao Peng
    Arxiv preprint, Feb 2024
    Paper Code
  8. NAACL 2024
    R-Tuning: Teaching Large Language Models to Refuse Unknown Questions
    Hanning Zhang*, Shizhe Diao*, Yong Lin*, Yi R. Fung, Qing Lian, Xingyao Wang, Yangyi Chen, Heng Ji, and Tong Zhang
    In Proceedings of the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), Jun 2024
    Paper Code
  9. NAACL 2024
    (Findings)
    LeTI: Learning to Generate from Textual Interactions
    Xingyao Wang, Hao Peng, Reyhaneh Jabbarvand, and Heng Ji
    In Findings of the Association for Computational Linguistics: (NAACL), Jun 2024
    Paper Code X/Twitter Thread

2023

  1. ACL 2023
    Code4Struct: Code Generation for Few-Shot Event Structure Prediction
    Xingyao Wang, Sha Li, and Heng Ji
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2023
    Paper Code X/Twitter Thread Poster
  2. EMNLP 2023
    ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation
    Yangyi Chen, Xingyao Wang, Manling Li, Derek Hoiem, and Heng Ji
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023
    Paper
  3. EMNLP 2023
    (Findings)
    Defining a New NLP Playground
    Sha Li, Chi Han, Pengfei Yu, Carl Edwards, Manling Li, Xingyao Wang, Yi Fung, Charles Yu, Joel Tetreault, Eduard Hovy, and Heng Ji
    In Findings of the Association for Computational Linguistics: EMNLP 2023, Dec 2023
    Paper

2022

  1. EMNLP 2022
    POTATO: The Portable Text Annotation Tool
    Jiaxin Pei, Aparna Ananthasubramaniam, Xingyao Wang, Naitian Zhou, Apostolos Dedeloudis, Jackson Sargent, and David Jurgens
    In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Dec 2022
    Paper Code

2021

  1. MLSys 2021
    Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters
    Shaohuai Shi*, Xianhao Zhou*, Shutao Song*, Xingyao Wang, Zilin Zhu, Xue Huang, Xinan Jiang, Feihu Zhou, Zhenyu Guo, Liqiang Xie, Rui Lan, Xianbin Ouyang, Yan Zhang, Jieqian Wei, Jing Gong, and 9 more authors
    In Proceedings of Machine Learning and Systems, Dec 2021
    Paper
  2. EMNLP 2021
    (Findings)
    An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog
    Xingyao Wang, and David Jurgens
    In Findings of the Association for Computational Linguistics: EMNLP 2021, Nov 2021
    Paper Code X/Twitter Thread Poster Presentation Video Imgur Post